LinArcX · December 13, 2020 16:29 · Jun 22, 2012 · Jun 3, 2012 · May 31, 2012 · May 31, 2012
diff --git a/html5TagSyntax.bnf b/html5TagSyntax.bnf
@@ -21,4 +21,4 @@ attr-double-quoted-value := /[^"]*/
 
 alphabets := [a-zA-Z]
 digits := /[0-9]/
-ws := /\s+/
+ws := /\s/
diff --git a/html5TagSyntax.bnf b/html5TagSyntax.bnf
@@ -1,4 +1,5 @@
-tag-open := '<' tag-name ws* attr-list? ws* '/'? '>'
+tag-open := '<' tag-name ws* attr-list? ws* '>'
+tag-empty := '<' tag-name ws* attr-list? ws* '/>'
 tag-close := '</' tag-name ws* '>'
 
 

diff --git a/htmlSyntax.bnf → html5TagSyntax.bnf b/htmlSyntax.bnf → html5TagSyntax.bnf
diff --git a/htmlSyntax.bnf b/htmlSyntax.bnf
@@ -1,19 +1,22 @@
-tag-open := '<' tag-name attributes ['/'] '>'
+tag-open := '<' tag-name ws* attr-list? ws* '/'? '>'
 tag-close := '</' tag-name ws* '>'
 
 
-attributes := (ws+ attr)*
-attr := empty | unquoted | single-quoted | double-quoted
-empty := attr-name
-unquoted := attr-name ws* = ws* attr-value-nonspace
-single-quoted := attr-name ws* = ws* ' attr-value-nosingle '
-double-quoted := attr-name ws* = ws* " attr-value-nodouble "
+attr-list := (ws+ attr)*
+attr := attr-empty | attr-unquoted | attr-single-quoted | attr-double-quoted
 
-tag-name := (alphabets | digits)+                              # can digits become first letter?
+attr-empty := attr-name
+attr-unquoted := attr-name ws* = ws* attr-unquoted-value
+attr-single-quoted := attr-name ws* = ws* ' attr-single-quoted-value '
+attr-double-quoted := attr-name ws* = ws* " attr-double-quoted-value "
+
+tag-name := (alphabets | digits)+                      # Can digits become first letter?
 attr-name := /[^\s"'>/=\p{Control}]+/
-attr-value-nosingle := /[^']*/
-attr-value-nodouble := /[^"]*/
-attr-value-nonspace := /[^\s"'=<>`]+/
+
+# These three items should not contain 'ambiguous ampersand'...
+attr-unquoted-value := /[^\s"'=<>`]+/
+attr-single-quoted-value := /[^']*/
+attr-double-quoted-value := /[^"]*/
 
 alphabets := [a-zA-Z]
 digits := /[0-9]/

diff --git a/htmlSyntax.bnf b/htmlSyntax.bnf
@@ -1,15 +1,16 @@
-opentag := '<' tagname attributes ['/'] '>'
-closetag := '</' tagname ws* '>'
-tagname := alphabets (alphabets | digits)*
+tag-open := '<' tag-name attributes ['/'] '>'
+tag-close := '</' tag-name ws* '>'
+
+
 attributes := (ws+ attr)*
 attr := empty | unquoted | single-quoted | double-quoted
 empty := attr-name
 unquoted := attr-name ws* = ws* attr-value-nonspace
 single-quoted := attr-name ws* = ws* ' attr-value-nosingle '
 double-quoted := attr-name ws* = ws* " attr-value-nodouble "
 
-tagname := /[a-zA-Z0-9]+/
-attr-name := /[^\s"'>/=]+/
+tag-name := (alphabets | digits)+                              # can digits become first letter?
+attr-name := /[^\s"'>/=\p{Control}]+/
 attr-value-nosingle := /[^']*/
 attr-value-nodouble := /[^"]*/
 attr-value-nonspace := /[^\s"'=<>`]+/

diff --git a/htmlSyntax.bnf b/htmlSyntax.bnf
@@ -0,0 +1,19 @@
+opentag := '<' tagname attributes ['/'] '>'
+closetag := '</' tagname ws* '>'
+tagname := alphabets (alphabets | digits)*
+attributes := (ws+ attr)*
+attr := empty | unquoted | single-quoted | double-quoted
+empty := attr-name
+unquoted := attr-name ws* = ws* attr-value-nonspace
+single-quoted := attr-name ws* = ws* ' attr-value-nosingle '
+double-quoted := attr-name ws* = ws* " attr-value-nodouble "
+
+tagname := /[a-zA-Z0-9]+/
+attr-name := /[^\s"'>/=]+/
+attr-value-nosingle := /[^']*/
+attr-value-nodouble := /[^"]*/
+attr-value-nonspace := /[^\s"'=<>`]+/
+
+alphabets := [a-zA-Z]
+digits := /[0-9]/
+ws := /\s+/